1234567891011121314151617181920212223242526272829303132333435363738394041 |
- From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
- From: Michael Yang <mxyng@pm.me>
- Date: Mon, 16 Sep 2024 15:53:13 -0700
- Subject: [PATCH] pretokenizer
- ---
- src/llama.cpp | 14 +++-----------
- 1 file changed, 3 insertions(+), 11 deletions(-)
- diff --git a/src/llama.cpp b/src/llama.cpp
- index abc1252e..626c3e3f 100644
- --- a/src/llama.cpp
- +++ b/src/llama.cpp
- @@ -6400,16 +6400,7 @@ static void llm_load_vocab(
- if (vocab.type == LLAMA_VOCAB_TYPE_BPE) {
- vocab.tokenizer_add_space_prefix = false;
- vocab.tokenizer_clean_spaces = true;
- - if (tokenizer_pre.empty()) {
- - LLAMA_LOG_WARN("%s: missing pre-tokenizer type, using: 'default'\n", __func__);
- - LLAMA_LOG_WARN("%s: \n", __func__);
- - LLAMA_LOG_WARN("%s: ************************************ \n", __func__);
- - LLAMA_LOG_WARN("%s: GENERATION QUALITY WILL BE DEGRADED! \n", __func__);
- - LLAMA_LOG_WARN("%s: CONSIDER REGENERATING THE MODEL \n", __func__);
- - LLAMA_LOG_WARN("%s: ************************************ \n", __func__);
- - LLAMA_LOG_WARN("%s: \n", __func__);
- - vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
- - } else if (tokenizer_pre == "default") {
- + if (tokenizer_pre == "default") {
- vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
- } else if (
- tokenizer_pre == "llama3" ||
- @@ -6514,7 +6505,8 @@ static void llm_load_vocab(
- tokenizer_pre == "minerva-7b") {
- vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_MINERVA;
- } else {
- - throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
- + LLAMA_LOG_WARN("%s: missing or unrecognized pre-tokenizer type, using: 'default'\n", __func__);
- + vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
- }
- } else if (vocab.type == LLAMA_VOCAB_TYPE_SPM) {
- vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
|